속성으로 검색

이 문서는 속성과 이름이 지정된 값으로 설명된 개체를 찾기 위한 간단한 탐색 인터페이스를 제공합니다. 그 밖에 사용 가능한 검색 인터페이스에는 문서 속성 검색 및 Ask 쿼리 빌더가 있습니다.

결과 목록

• Lesson:papi exploiting dynamic parallelism in large language model decoding with a processing in memory 5f9f53cc  + (Large-model inference platforms with GPU and PIM execution support. Limits: Benefits depend on specialized PIM hardware and the evaluated model/kernel mix.)
• Lesson:stem streaming based fpga acceleration for large scale compactions in lsm kv d204166c  + (Large-scale LSM compaction on FPGA-enabled storage servers. Limits: Benefits depend on FPGA resources, host/storage balance, and the evaluated compaction distributions.)
• Lesson:fetchbpf customizable prefetching policies in linux with ebpf 9756cb90  + (Linux VM prefetch experimentation and workload-specific deployment. Limits: The demonstrated domain is prefetching; eBPF verifier and helper interfaces bound policy expressiveness.)
• Lesson:scalecache a scalable page cache for multiple solid state drives 60b5c227  + (Linux file systems on multi-NVMe servers. Limits: Results depend on the evaluated 64-core/eight-drive platform and altered page-cache/writeback semantics.)
• Lesson:rearchitecting buffered i o in the era of high bandwidth ssd 70b23de3  + (Linux filesystems on high-bandwidth SSDs, especially partial/unaligned writes. Limits: Headline results focus on evaluated filesystems/devices; adds a new buffering/flushing architecture.)
• Lesson:flexmem adaptive page profiling and migration for tiered memory 43991e2a  + (Linux heterogeneous/tiered-memory systems. Limits: Tuning and gains depend on hardware counters, memory topology, migration costs, and workload phase length.)
• Lesson:ozz identifying kernel out of order concurrency bugs with in vivo memory access reordering 0b85f639  + (Linux kernel concurrency testing, memory-barrier validation, and fuzzing. Limits: Emulation coverage is bounded by the modeled memory behavior and explored schedules; findings focus on Linux.)
• Lesson:technical review scoz a system wide causal profiler for multicore systems 9ddaf48a  + (Linux multiprocess/MPI 및 kernel-intensive workload의 최적화 우선순위 탐색에 높음.)
• Lesson:scoz a systemwide causal profiler for multicore systems 7b5e72e2  + (Linux multiprocess/MPI 및 kernel-intensive workload의 최적화 우선순위 탐색에 높음.)
• Lesson:fast flexible and practical kernel extensions 9eb8897f  + (Linux networking, observability, and in-kernel extension frameworks. Limits: Runtime checks, cancellation, and verifier assumptions remain in the TCB; full upstream integration is incomplete.)
• Lesson:fast trapless kernel probes everywhere 781e739b  + (Linux tracing, observability, and security instrumentation. Limits: Needs toolchain/kernel-layout changes; some code and architectures remain unsupported.)
• Lesson:chrono meticulous hotness measurement and flexible page migration for memory tiering 840ae980  + (Linux-managed DRAM+Optane/CXL-like tiered … Linux-managed DRAM+Optane/CXL-like tiered memory; base-page workloads with changing access distributions.</br></br>Limits: Evaluated on one 64GB/256GB DRAM-Optane platform; benefits and auto-tuning may vary with device latency/bandwidth, page size, and workload stability. Under huge pages Memtis was 1.03× faster in one Graph500 setting. was 1.03× faster in one Graph500 setting.)
• Lesson:compare identical source envelopes at long run boundaries 5f58511d  + (Long-running GPU experiments, training jobs, migrations, and any fail-closed pipeline that validates provenance only after expensive work.)
• Lesson:fast core scheduling with userspace process abstraction d1ea9f62  + (Low-latency core scheduling and colocated services on UINTR/MPK-capable CPUs. Limits: Requires userspace interrupts, MPK, shared-process abstractions, and constrained syscall behavior; numeric evaluation not verified.)
• Lesson:combining buffered i o and direct i o in distributed file systems b0e268e6  + (Lustre·HPC 분산 파일시스템. Limits: Lustre/HPC 중심이며 임계값과 워크로드 변화에 민감하다.)
• Lesson:technical review mp bcoz 4fde17b0  + (MPI·분산 학습·멀티프로세스 서버의 성능 병목 우선순위 결정.)
• Lesson:mp bcoz ea8563ba  + (MPI·분산 학습·멀티프로세스 서버의 성능 병목 우선순위 결정.)
• Lesson:corobase coroutine oriented main memory database engine c4a28018  + (Main-memory databases with pointer-heavy read paths. Limits: Benefits shrink for compute/write-heavy workloads and depend on useful prefetch distance and batching concurrency.)
• Lesson:scalable address spaces using concurrent interval skiplist d1f1b9c0  + (Many-core kernels and mmap-intensive applications. Limits: Kernel-specific implementation and results on one 48-core platform; complex interval semantics remain workload-dependent.)
• Lesson:harvesting memory bound cpu stall cycles in software with msh 5866da08  + (Memory-bound server workloads with latency SLOs and spare CPU cycles. Limits: Requires analyzable/instrumentable binaries and enough predictable memory stalls; abstract does not enumerate all workloads.)
• Lesson:swam revisiting swap and oomk for improving application responsiveness on mobile devices 79b3b8a3  + (Memory-constrained mobile operating systems. Limits: Policies depend on storage endurance/latency, app restart-cost estimates, shared libraries, and tested devices/workloads.)
• Lesson:pmr fast application response via parallel memory reclaim on mobile devices 4c59e491  + (Memory-constrained mobile systems with flash-backed swapping/writeback. Limits: Reported evaluation is mobile/Android-specific; energy and flash-wear effects were not in the accessible abstract.)
• Lesson:klotski efficient mixture of expert inference via expert aware multi batch pipeline bae4ea7b  + (Memory-constrained, CPU/disk-offloaded MoE batch inference. Limits: Preprint-only record; gains are hardware/model/batch dependent, and more batches increase KV-cache load and latency.)
• Lesson:archer adaptive memory compression with page association rule awareness for high speed response 98bcc760  + (Mobile anonymous memory with recurring or correlated page content. Limits: Correlation discovery and benefits depend on app mix; results target mobile workloads.)
• Lesson:separate semantic replication hashes from provenance bound artifact hashes e7ab7a4e  + (Model calibration reruns, migration candidates, deterministic inference artifacts, and any replicated experiment whose control-plane provenance changes while the scientific payload should not.)
• Lesson:scale and flexibility in distribution of hot content a83ac58f  + (Most directly applicable to high-fanout object distribution inside a managed private cloud. The official abstract does not establish equivalent behavior on open or adversarial networks.)

• Lesson:efficient footprint caching for tagless dram caches 9317d60c  + (Multi-GB in-package DRAM cache와 TDC 계열 구조에 해당한다.)
• Lesson:technical review efficient footprint caching for tagless dram caches 5090e3ab  + (Multi-GB in-package DRAM cache와 TDC 계열 구조에 해당한다.)

• Lesson:serverlessllm low latency serverless inference for large language models 69b8cd6d  + (Multi-model serverless LLM inference clusters. Limits: Benefits depend on local checkpoint capacity, locality, storage bandwidth, model size, and loading-dominated workloads.)
• Lesson:pacar improved buffered i o locality on numa systems with page cache replication adc0c538  + (Multi-socket NUMA servers running buffered file I/O. Limits: Current implementation does not support mmap; write-heavy benefits are constrained by invalidation/coherence.)
• Lesson:mitigating application resource overload with targeted task cancellation 90270bf8  + (Multi-stage services with cancellable task … Multi-stage services with cancellable tasks and application-visible lock, pool, memory, queue, CPU, or I/O overload.</br></br>Limits: Integration required manual annotation, only marked-safe tasks can be cancelled, and results cover six applications and 16 reproduced cases. six applications and 16 reproduced cases.)
• Lesson:citadel rethinking memory allocation to safeguard against inter domain rowhammer exploits 8fd39aca  + (Multi-tenant DRAM systems needing inter-domain RowHammer isolation. Limits: Assumes known DRAM row mapping/geometry and protects inter-domain placement rather than every RowHammer vector.)
• Lesson:vfpio a virtual i o abstraction for fpga accelerated i o devices dcc63d73  + (Multi-tenant FPGA-accelerated I/O services. Limits: Requires FPGA integration and trusted scheduling policy; evidence is tied to U280/Coyote and evaluated interfaces.)
• Lesson:lithos an operating system for efficient machine learning on gpus 76d95512  + (Multi-tenant GPUs running inference and mixed ML jobs. Limits: Requires a specialized GPU OS/runtime and kernel atomization; gains vary by workload interference.)
• Lesson:dlora dynamically orchestrating requests and adapters for lora llm serving 3827bfa3  + (Multi-tenant LoRA serving with many adapters and skewed arrivals. Limits: Performance depends on adapter popularity, merge/migration cost, model size, and workload dynamics.)
• Lesson:fleetio managing multi tenant cloud storage with multi agent reinforcement learning 714ca9fb  + (Multi-tenant cloud SSD virtualization and programmable storage. Limits: RL behavior depends on training coverage, reward tuning, trace stationarity, programmable-device features, and SLO definitions.)
• Lesson:not a dpu in name only unleashing rdma capable dpus in multi tenant serverless clouds with nadin 7031318c  + (Multi-tenant serverless clouds with programmable RDMA DPUs. Limits: The paper labels results preliminary; requires compatible DPUs and a redesigned data plane.)
• Lesson:deltazip efficient serving of multiple full model tuned llms 8420449f  + (Multi-tenant serving of full- or parameter-efficiently fine-tuned models sharing a base. Limits: Prompt computation is not accelerated; gains narrow at uniformly high load, and compression needs calibration plus known base lineage.)
• Lesson:cost efficient large language model serving for multi turn conversations with cachedattention aa200b5c  + (Multi-turn chatbot and agent services with repeated conversation prefixes. Limits: Benefits depend on prefix reuse, storage bandwidth/capacity, context truncation, and scheduler locality.)
• Lesson:technical review cache scheme of shared buffer mappings for energy efficiency of mobile devices f1dee859  + (Multimedia buffer를 application과 device가 반복 공유하는 mobile SoC에 해당한다.)
• Lesson:cache scheme of shared buffer mappings for energy efficiency of mobile devices 4b6db791  + (Multimedia buffer를 application과 device가 반복 공유하는 mobile SoC에 해당한다.)
• Lesson:tiered memory management access latency is the key aaf24437  + (NUMA-, CXL-, and heterogeneous-memory tiering with separate channels. Limits: Requires distinguishable tier traffic and reliable counters; evaluation uses NUMA as a tiered-memory proxy.)
• Lesson:tierscape harnessing multiple compressed tiers to tame server memory tco 9ed9ed0d  + (NUMA/CXL/Optane servers with byte-addressable and optional compressed tiers. Limits: Reproducing performance requires Optane-like latency; compression needs a Linux 5.17 patch, at least two NUMA nodes, and artifact result reproduction is marked TODO.)
• Lesson:research autopilot 20260718t030144z-gpu  + (NVIDIA L40S GPU 3, 기록된 shape·dtype·커밋·벤치마크 구현에만 적용한다. 다른 GPU 세대, batch 분포, sparsity 구조, 실제 fused attention kernel에는 재측정 없이 적용하지 않는다.)
• Lesson:enabling high performance and secure userspace nvm file systems with the trio architecture d59d00b6  + (NVM 기반 사용자 공간 파일시스템. Limits: NVM과 특정 handoff·신뢰 모델, 파일시스템별 핵심 상태 설계가 필요하다.)
• Lesson:light dedup a light weight inline deduplication framework for non volatile memory file systems 000ae22e  + (NVM 파일시스템 inline dedup. Limits: 중복·지역성 정도와 NVM 특성에 민감하며 일부 결과는 crafted aging workload다.)
• Lesson:technical review nvme prp zero copy cb4e87d1  + (NVMe read path의 copy 제거 설계 검토에 한정합니다. 현재 자료만으로 안전성이나 성능 개선을 일반화하지 않습니다.)
• Lesson:byteexpress a high performance and traffic efficient inline transfer of small payloads over nvme a7c01a49  + (NVMe workloads dominated by small reads/writes on modifiable controllers. Limits: Prototype uses OpenSSD and targets sub-page payloads; benefit does not generalize to large transfers.)
• Lesson:technical review nvme d8da4781  + (NVMe 다중 큐 I/O scheduling 비교에 한정합니다. 현재 자료는 특정 스케줄러의 우월성을 검증하지 못합니다.)
• Lesson:i o passthru upstreaming a flexible and efficient i o path in linux 7b568465  + (NVMe 최적화 DB·캐시·스토리지 엔진. Limits: 범용 블록 서비스 일부를 우회하고 NVMe·peak FIO 중심 결과다.)
• Lesson:scalio scaling up dpu based jbof key value store with nvme of target offload 8db39764  + (NVMe-oF JBOF systems with programmable DPUs. Limits: Requires DPU-capable infrastructure and targets high-density configurations.)
• Lesson:a comprehensive analysis of superpage management mechanisms and policies c34f2dbd  + (OS huge-page/superpage management on server workloads. Limits: Quantitative results and hardware/workload scope remain abstract-only.)